Loading…
PaperMage is an open-source Python toolkit for analyzing and processing visually rich, structured scientific documents by providing clean abstractions for textual and visual elements. It unifies state-of-the-art NLP and CV models within a single framework and offers turnkey recipes for common scientific-document processing tasks. It has powered research prototypes and Semantic Scholar's large-scale production system for processing millions of PDFs and is part of the broader Semantic Reader Open Research Platform.
AI named Papermage in January 2026.